User | edsonchan |
Upload Date | May 20 2025 06:32 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.5 (Build 24F74) |
Model | Mac mini (2024) |
Model ID | Mac16,11 |
Motherboard | Mac16,11 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.50 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2050
381.3 IPS |
|
Image Classification (HP)
|
100% |
17920
3.33 KIPS |
|
Image Classification (Q)
|
97% |
22620
4.22 KIPS |
|
Image Segmentation (SP)
|
100% |
2309
37.4 IPS |
|
Image Segmentation (HP)
|
100% |
23329
378.2 IPS |
|
Image Segmentation (Q)
|
99% |
33115
536.8 IPS |
|
Pose Estimation (SP)
|
100% |
17108
20.0 IPS |
|
Pose Estimation (HP)
|
100% |
122705
143.2 IPS |
|
Pose Estimation (Q)
|
95% |
231504
271.3 IPS |
|
Object Detection (SP)
|
100% |
2483
196.9 IPS |
|
Object Detection (HP)
|
100% |
20615
1.64 KIPS |
|
Object Detection (Q)
|
91% |
25197
2.01 KIPS |
|
Face Detection (SP)
|
100% |
4620
54.9 IPS |
|
Face Detection (HP)
|
100% |
45407
539.5 IPS |
|
Face Detection (Q)
|
100% |
66252
787.2 IPS |
|
Depth Estimation (SP)
|
100% |
8626
66.5 IPS |
|
Depth Estimation (HP)
|
99% |
112449
866.4 IPS |
|
Depth Estimation (Q)
|
85% |
178632
1.40 KIPS |
|
Style Transfer (SP)
|
100% |
25849
33.2 IPS |
|
Style Transfer (HP)
|
100% |
239189
307.5 IPS |
|
Style Transfer (Q)
|
96% |
300893
388.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
5969
220.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
47159
1.74 KIPS |
|
Image Super-Resolution (Q)
|
99% |
80103
2.96 KIPS |
|
Text Classification (SP)
|
100% |
2882
3.85 KIPS |
|
Text Classification (HP)
|
100% |
7676
10.2 KIPS |
|
Text Classification (Q)
|
93% |
6762
9.08 KIPS |
|
Machine Translation (SP)
|
100% |
5615
96.7 IPS |
|
Machine Translation (HP)
|
100% |
17315
298.3 IPS |
|
Machine Translation (Q)
|
98% |
16656
287.8 IPS |